Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 105 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.9581. Min Act: -0.1700
Data Index: 4472798 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.9268. Min Act: -0.1700
Data Index: 6331948 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.8017. Min Act: -0.1700
Data Index: 1988585 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.8017. Min Act: -0.1700
Data Index: 7295683 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.7705. Min Act: -0.1700
Data Index: 208569 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.8017. Min Act: -0.1700
Data Index: 3018893 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.7861. Min Act: -0.1700
Data Index: 7211023 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.7392. Min Act: -0.1700
Data Index: 1377800 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.7079. Min Act: -0.1700
Data Index: 6755776 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.6923. Min Act: -0.1700
Data Index: 2008548 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.7079. Min Act: -0.1700
Data Index: 4914074 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.7079. Min Act: -0.1700
Data Index: 2898333 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.6766. Min Act: -0.1700
Data Index: 451846 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.6923. Min Act: -0.1700
Data Index: 1190319 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.6610. Min Act: -0.1700
Data Index: 4327455 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.6610. Min Act: -0.1700
Data Index: 7645345 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.6610. Min Act: -0.1700
Data Index: 5956561 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.6610. Min Act: -0.1700
Data Index: 2161136 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.6610. Min Act: -0.1700
Data Index: 1317378 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9581. Min Range: -3.9581
Max Act: 3.6610. Min Act: -0.1700
Data Index: 6622117 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19